Custom-Parameter GGUF LLModels for Text, Code & Math

• Model 1

  Node Name: ⬢ MATH EQUATIONS & REASONING: Palmyra-Mini-Thinking-B 1.78B Q4

  LLM_HF_REPO: prithivMLmods/palmyra-mini-thinking-AIO-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: palmyra-mini-thinking-b-GGUF/palmyra-mini-thinking-b.Q4_K_M.gguf Copy Copied!

• Model 2

  Node Name: ⬢ COMPLEX LOGIC & REASONING: Palmyra-Mini-Thinking-A 1.78B Q4

  LLM_HF_REPO: prithivMLmods/palmyra-mini-thinking-AIO-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: palmyra-mini-thinking-a-GGUF/palmyra-mini-thinking-a.Q4_K_M.gguf Copy Copied!

• Model 3

  Node Name: ⬢ CODING & TEXT GEN: CodeGemma-1.1-2B Q4

  LLM_HF_REPO: bartowski/codegemma-2b-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: codegemma-2b-Q4_K_M.gguf Copy Copied!

• Model 4

  Node Name: ⬢ CODING & MATH: DeepSeek-Coder-1.3B Q4

  LLM_HF_REPO: TheBloke/deepseek-coder-1.3b-base-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: deepseek-coder-1.3b-base.Q4_K_M.gguf Copy Copied!

• Model 5

  Node Name: ⬢ TEXT & MATH GEN: Qwen2.5-1.5B Q4

  LLM_HF_REPO: bartowski/Qwen2.5-1.5B-Instruct-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Qwen2.5-1.5B-Instruct-Q4_K_M.gguf Copy Copied!

• Model 6

  Node Name: ⬢ GENERAL TEXT & REASONING: Llama-3.2-1B Q4

  LLM_HF_REPO: bartowski/Llama-3.2-1B-Instruct-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Llama-3.2-1B-Instruct-Q4_K_M.gguf Copy Copied!

• Model 7

  Node Name: ⬢ MULTILINGUAL TEXT & MATH: Gemma-2-2B Q4

  LLM_HF_REPO: bartowski/gemma-2-2b-it-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: gemma-2-2b-it-Q4_K_M.gguf Copy Copied!

• Model 8

  Node Name: ⬢ REASONING & CODING: Phi-3-mini-3.8B Q4

  LLM_HF_REPO: bartowski/Phi-3.1-mini-4k-instruct-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Phi-3.1-mini-4k-instruct-Q4_K_M.gguf Copy Copied!

• Model 9

  Node Name: ⬢ Gensyn/Qwen2.5-1.5B-Instruct - GGUF Q4

  LLM_HF_REPO: tensorblock/Gensyn_Qwen2.5-1.5B-Instruct-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Qwen2.5-1.5B-Instruct-Q4_K_M.gguf Copy Copied!

• Model 10

  Node Name: ⬢ CHAT & CODING: StableLM-2-Zephyr-1.6B Q4

  LLM_HF_REPO: TheBloke/stablelm-zephyr-3b-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: stablelm-zephyr-3b.Q4_K_M.gguf Copy Copied!

• Model 11

  Node Name: ⬢ MATH & REASONING: SmolLM3-3B Q4

  LLM_HF_REPO: ggml-org/SmolLM3-3B-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: SmolLM3-Q4_K_M.gguf Copy Copied!

• Model 12

  Node Name: ⬢ Causal Language Model (Fine-tuned with LoRA)

  LLM_HF_REPO: mradermacher/Genuine-1B-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Genuine-1B.Q4_K_M.gguf Copy Copied!

• Model 13

  Node Name: ⬢ TEXT GENERATION: Qwen3-1.7B Q4

  LLM_HF_REPO: unsloth/Qwen3-1.7B-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Qwen3-1.7B-Q4_K_M.gguf Copy Copied!

• Model 14

  Node Name: ⬢ INSTRUCT TEXT & MATH: Gemma-1.1-2B-IT Q4

  LLM_HF_REPO: lmstudio-community/gemma-1.1-2b-it-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: gemma-1.1-2b-it-Q4_K_M.gguf Copy Copied!

• Model 15

  Node Name: ⬢ DeepseekR1 & Qwen - DeepSeek-R1-Distill-Qwen-1.5B Q4

  LLM_HF_REPO: unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf Copy Copied!

• Model 16

  Node Name: ⬢ ADVANCED CODING & MATH: DeepSeek-Coder-V2-Lite-1.3B Q4

  LLM_HF_REPO: TheBloke/deepseek-coder-1.3b-instruct-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: deepseek-coder-1.3b-instruct.Q4_K_M.gguf Copy Copied!

• Model 17

  Node Name: ⬢ CODE GEN & TEXT: tinylama-rust-1B Q4

  LLM_HF_REPO: vasu14devagarwal/tinylama-rust-Q4_K_M-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: tinylama-rust-q4_k_m.gguf Copy Copied!

• Model 18

  Node Name: ⬢ MATH & REASONING: SmolLM3-3B Q4

  LLM_HF_REPO: ggml-org/SmolLM3-3B-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: SmolLM3-Q4_K_M.gguf Copy Copied!

• Model 19

  Node Name: ⬢ ULTRA LIGHT : Fine-tuned Tesslate/Rust_Dataset Q4

  LLM_HF_REPO: mradermacher/Tiny-OR1-Rust-GGUF Copy Copied!

  LLM_HF_MODEL_NAME: Tiny-OR1-Rust.Q4_K_M.gguf Copy Copied!